Academic Commons

Articles

A Discriminative Model for Polyphonic Piano Transcription

Poliner, Graham E.; Ellis, Daniel P. W.

We present a discriminative model for polyphonic piano transcription. Support vector machines trained on spectral features are used to classify frame-level note instances. The classifier outputs are temporally constrained via hidden Markov models, and the proposed system is used to transcribe both synthesized and real piano recordings. A frame-level transcription accuracy of 68% was achieved on a newly generated test set, and direct comparisons to previous approaches are provided.

Files

Also Published In

Title
EURASIP Journal on Advances in Signal Processing
DOI
https://doi.org/10.1155/2007

More About This Work

Academic Units
Electrical Engineering
Published Here
February 13, 2012